{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T04:26:21Z","timestamp":1743567981257,"version":"3.40.3"},"reference-count":99,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T00:00:00Z","timestamp":1713916800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T00:00:00Z","timestamp":1713916800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-19121-y","type":"journal-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T05:02:01Z","timestamp":1713934921000},"page":"7319-7359","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A novel framework for under-determined blind source separation based on adaptive source counting using mixed linear and circular data clustering algorithm for low latency applications"],"prefix":"10.1007","volume":"84","author":[{"given":"Mahdi","family":"Khademi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1174-2280","authenticated-orcid":false,"given":"Sayeh","family":"Mirzaei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaser","family":"Norouzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,24]]},"reference":[{"key":"19121_CR1","doi-asserted-by":"publisher","unstructured":"Douglas S (2001) Microphone Arrays. ch. Blind Separation of Acoustic Signals, Signal Processing Techniques and Applications, Springer https:\/\/doi.org\/10.1007\/978-3-662-04619-7_16","DOI":"10.1007\/978-3-662-04619-7_16"},{"key":"19121_CR2","doi-asserted-by":"publisher","first-page":"2025","DOI":"10.1109\/TASLP.2020.3003855","volume":"28","author":"T Sgouros","year":"2020","unstructured":"Sgouros T, Mitianoudis N (2020) A novel Directional Framework for Source Counting and Source Separation in Instantaneous Underdetermined Audio Mixtures. IEEE\/ACM Trans Audio, Speech Lang Process 28:2025\u20132035","journal-title":"IEEE\/ACM Trans Audio, Speech Lang Process"},{"key":"19121_CR3","doi-asserted-by":"publisher","unstructured":"Hyvarinen A, Hoyer P, Oja E (1998) Sparse code shrinkage for image denoising. In: 1998 IEEE international joint conference on neural networks proceedings, IEEE world congress on computational intelligence (Cat. No.98CH36227), vol 2, Anchorage, pp 859\u2013864. https:\/\/doi.org\/10.1109\/IJCNN.1998.685880","DOI":"10.1109\/IJCNN.1998.685880"},{"key":"19121_CR4","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.jneumeth.2018.12.007","volume":"315","author":"C Chatzichristos","year":"2019","unstructured":"Chatzichristos C, Kofidis E, Morante M, Theodoridis S (2019) Blind fMRI source unmixing via higher-order tensor decompositions. J Neurosci Methods 315:17\u201347","journal-title":"J Neurosci Methods"},{"key":"19121_CR5","doi-asserted-by":"publisher","unstructured":"Cichoki A, Amari S (2002) Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications, John Wiley & Sons. https:\/\/doi.org\/10.1002\/0470845899","DOI":"10.1002\/0470845899"},{"issue":"2","key":"19121_CR6","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1109\/97.300310","volume":"1","author":"S Talwar","year":"1994","unstructured":"Talwar S, Viberg M, Paulraj A (1994) Blind estimation of multiple co-channel digital signals using an antenna array. IEEE Signal Process Lett 1(2):29\u201331","journal-title":"IEEE Signal Process Lett"},{"key":"19121_CR7","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1016\/j.sigpro.2016.12.001","volume":"134","author":"C Llerena-Aguilar","year":"2017","unstructured":"Llerena-Aguilar C, Gil-Pita R, Utrilla-Manso M, Rosa-Zurera M (2017) A new mixing matrix estimation method based on the geometrical analysis of the sound separation problem. Signal Process 134:166\u2013173","journal-title":"Signal Process"},{"key":"19121_CR8","doi-asserted-by":"publisher","unstructured":"Mahdi Khademi, Sayeh Mirzaei, Yaser Norouzi (2021) High resolution sub-band decomposition underdetermined blind signal separation using virtual sensor based ICA method for low latency applications, Digital Signal Process, vol. 113. https:\/\/doi.org\/10.1016\/j.dsp.2021.103015","DOI":"10.1016\/j.dsp.2021.103015"},{"key":"19121_CR9","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.sigpro.2015.03.006","volume":"115","author":"S Mirzaei","year":"2015","unstructured":"Mirzaei S (2015) Hugo Van hamme, Yaser Norouzi, Blind audio source counting and separation of anechoic mixtures using the multichannel complex NMF framework, Elsevier. Signal Process 115:27\u201337","journal-title":"Signal Process"},{"key":"19121_CR10","doi-asserted-by":"publisher","unstructured":"Van Hamme H, Norouzi Y, Mirzaie S (2015) Two-stage blind audio source counting and separation of stereo instantaneous mixtures using Bayesian tensor factorisation. IET Signal Process. https:\/\/doi.org\/10.1049\/iet-spr.2014.0404","DOI":"10.1049\/iet-spr.2014.0404"},{"key":"19121_CR11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-217","volume-title":"Proceedings of the annual conference of the international speech communication association","author":"S Mirzaie","year":"2014","unstructured":"Mirzaie S, Van Hamme H, Norouzi Y (2014) Blind speech source localization, counting and separation for 2-channel convolutive mixtures in a reverberant environment. In: Proceedings of the annual conference of the international speech communication association. INTERSPEECH. https:\/\/doi.org\/10.21437\/Interspeech.2014-217"},{"key":"19121_CR12","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.dsp.2019.01.022","volume":"87","author":"Y Xie","year":"2019","unstructured":"Xie Y, Xie K, Xie S (2019) Underdetermined convolutive blind separation of sources integrating tensor factorization and expectation maximization. Digital Signal Processing 87:145\u2013154","journal-title":"Digital Signal Processing"},{"issue":"692","key":"19121_CR13","first-page":"730","volume":"25","author":"S Gannot","year":"2017","unstructured":"Gannot S, Vincent E, Golan Shmulik Markovich, Ozerov Alexey (2017) A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation. IEEE\/ACM Trans Audio, Speech Lang Process 25(692):730","journal-title":"IEEE\/ACM Trans Audio, Speech Lang Process"},{"key":"19121_CR14","doi-asserted-by":"publisher","unstructured":"Togami M (2011) Online speech source separation based on maximum likelihood of local Gaussian modeling. In: 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP), Prague, pp 213\u2013216. https:\/\/doi.org\/10.1109\/ICASSP.2011.5946378","DOI":"10.1109\/ICASSP.2011.5946378"},{"issue":"397","key":"19121_CR15","first-page":"404","volume":"7191","author":"SRS Laurent","year":"2012","unstructured":"Laurent SRS, Vincent E (2012) A General Framework for Online Audio Source Separation. Latent Variable Anal Signal Separation 7191(397):404","journal-title":"Latent Variable Anal Signal Separation"},{"key":"19121_CR16","doi-asserted-by":"publisher","unstructured":"Ikeshita R, Togami M, Kawaguchi Y, Fujita Y, Nagamatsu K (2017) Local Gaussian model with source-set constraints in audio source separation. In: 2017 IEEE 27th international workshop on machine learning for signal processing (MLSP). IEEE, Tokyo, Japan, pp 1\u20136. https:\/\/doi.org\/10.1109\/MLSP.2017.8168170","DOI":"10.1109\/MLSP.2017.8168170"},{"key":"19121_CR17","volume-title":"Speech coding and synthesis","author":"WB Kleijn","year":"1995","unstructured":"Kleijn WB, Paliwal KK (1995) Speech coding and synthesis. Elsevier, Amsterdam"},{"issue":"34","key":"19121_CR18","first-page":"42","volume":"93","author":"S Shahnawazuddin Nagaraj Adiga","year":"2019","unstructured":"Shahnawazuddin Nagaraj Adiga S, Tarun Sai B, Ahmad Waquar, Kathania Hemant K (2019) Developing speaker independent ASR system using limited data through prosody modification based on fuzzy classification of spectral bins. Digital Signal Processing 93(34):42","journal-title":"Digital Signal Processing"},{"key":"19121_CR19","doi-asserted-by":"publisher","unstructured":"Hyvarinen A, Karhunen J, Oja E (2001) Independent component analysis. John Wiley & Sons. https:\/\/doi.org\/10.1002\/0471221317","DOI":"10.1002\/0471221317"},{"key":"19121_CR20","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1023\/A:1008324625522","volume":"16","author":"P Bradley","year":"2000","unstructured":"Bradley P, Mangasarian O (2000) k-Plane Clustering. J Glob Optim 16:23\u201332. https:\/\/doi.org\/10.1023\/A:1008324625522","journal-title":"J Glob Optim"},{"key":"19121_CR21","doi-asserted-by":"publisher","first-page":"29845","DOI":"10.1109\/ACCESS.2019.2902620","volume":"7","author":"X Yang","year":"2019","unstructured":"Yang X et al (2019) Piecewise Linear Regression Based on Plane Clustering. IEEE Access 7:29845\u201329855","journal-title":"IEEE Access"},{"issue":"2","key":"19121_CR22","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1162\/089976699300016719","volume":"11","author":"TW Lee","year":"1999","unstructured":"Lee TW, Girolami M, Sejnowski TJ (1999) Independent component analysis using an extended infomax algorithm for mixed sub-Gaussian and super-Gaussian sources. Neural Comput 11(2):417\u2013441","journal-title":"Neural Comput"},{"key":"19121_CR23","doi-asserted-by":"publisher","unstructured":"Khani MM, Kahaei MH (2009) Blind source separation using virtual sensors. In: 2009 fourth international conference on digital telecommunications. Colmar, pp 107\u2013110. https:\/\/doi.org\/10.1109\/ICDT.2009.27","DOI":"10.1109\/ICDT.2009.27"},{"issue":"3","key":"19121_CR24","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1016\/j.neucom.2015.08.008","volume":"173","author":"J Sun","year":"2016","unstructured":"Sun J, Li Y, Wen J, Yan S (2016) Novel mixing matrix estimation approach in underdetermined blind source separation. Neurocomputing 173(3):623\u2013632","journal-title":"Neurocomputing"},{"key":"19121_CR25","doi-asserted-by":"publisher","unstructured":"Nesta F, Omologo M (2012) Convolutive underdetermined source separation through weighted interleaved ICA and spatio-temporal source correlation, in: Latent Variable Analysis and Signal Separation International Conference, pp. 222\u2013230 https:\/\/doi.org\/10.1007\/978-3-642-28551-6_28","DOI":"10.1007\/978-3-642-28551-6_28"},{"issue":"4","key":"19121_CR26","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1109\/89.242486","volume":"1","author":"E Weinstein","year":"1993","unstructured":"Weinstein E, Feder M, Oppenheim A (1993) Multi-Channel Signal Separation by Decorrelation. IEEE Trans on Speech and Audio Processing 1(4):405\u2013413","journal-title":"IEEE Trans on Speech and Audio Processing"},{"issue":"2","key":"19121_CR27","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1109\/78.554307","volume":"45","author":"A Belouchrani","year":"1997","unstructured":"Belouchrani A, Abed-Meraim K, Cardoso J, Moulines E (1997) A Blind Source Separation Technique using Second Order Statistics. IEEE Trans on Signal Processing 45(2):434\u2013444","journal-title":"IEEE Trans on Signal Processing"},{"key":"19121_CR28","doi-asserted-by":"publisher","unstructured":"Hacihabiboglu H (2016) Acoustic source separation using the short-time quaternion Fourier transforms of particle velocity signals. In: 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, Shanghai, pp 425\u2013429. https:\/\/doi.org\/10.1109\/ICASSP.2016.7471710","DOI":"10.1109\/ICASSP.2016.7471710"},{"issue":"4","key":"19121_CR29","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"Vincent E, Gribonval R, Fevotte C (2006) Performance measurement in blind audio source separation. IEEE Trans Audio Speech Lang Process 14(4):1462\u20131469","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"10","key":"19121_CR30","doi-asserted-by":"publisher","first-page":"2009","DOI":"10.1109\/5.720250","volume":"9","author":"J Cardoso","year":"1998","unstructured":"Cardoso J (1998) Blind Signal Separation: Statistical Properties. IEEE Proceedings 9(10):2009\u20132026","journal-title":"IEEE Proceedings"},{"key":"19121_CR31","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.specom.2017.12.010","volume":"96","author":"M Jia","year":"2018","unstructured":"Jia M, Sun J, Bao C, Ritz C (2018) Separation of multiple speech sources by recovering sparse and non-sparse components from B-format microphone recordings. Speech Commun 96:184\u2013196","journal-title":"Speech Commun"},{"issue":"1","key":"19121_CR32","first-page":"1","volume":"6","author":"S Choi","year":"2005","unstructured":"Choi S, Cichoki A, Park H, Lee S (2005) Blind Source Separation and Independent Component Analysis: A Review. Neural Information Processing 6(1):1\u201356","journal-title":"Neural Information Processing"},{"key":"19121_CR33","doi-asserted-by":"publisher","unstructured":"Grady P, Peralmutter B, Rickard S (2005) Survey of Sparse and Non-Sparse Methods in Source Separation, Int J Imaging Syst Technol, vol. 15 (1). https:\/\/doi.org\/10.1002\/ima.20035","DOI":"10.1002\/ima.20035"},{"issue":"2","key":"19121_CR34","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1109\/TASLP.2017.2774925","volume":"26","author":"J Nikunen","year":"2017","unstructured":"Nikunen J, Diment A, Virtanen T (2017) Separation of moving sound sources using multichannel NMF and acoustic tracking. IEEE\/ACM Trans Audio Speech Lang Process 26(2):281\u2013295","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"19121_CR35","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.specom.2016.01.003","volume":"81","author":"S Mirzaei","year":"2016","unstructured":"Mirzaei S, Van Hamme H, Norouzi Y (2016) Under-determined reverberant audio source separation using Bayesian non-negative matrix factorization. Speech Commun 81:129\u2013137. https:\/\/doi.org\/10.1016\/j.specom.2016.01.003","journal-title":"Speech Commun"},{"key":"19121_CR36","unstructured":"Sayeh Mirzaei, Hugo Van hamme, Yaser Norouzi (2014) Blind audio source separation of stereo mixtures using Bayesian Non-negative Matrix Factorization, European Signal Processing Conference - EUSIPCO, Lisbon, Portugl"},{"issue":"2","key":"19121_CR37","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/MSP.2013.2297439","volume":"32","author":"A Cichocki","year":"2015","unstructured":"Cichocki A, Mandic D, Lathauwer LD, Zhou G, Zhao Caiafa Q (2015) Tensor decompositions for signal processing applications: from two-way to multiway component analysis. IEEE Signal Process Mag 32(2):145\u2013163","journal-title":"IEEE Signal Process Mag"},{"issue":"3","key":"19121_CR38","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1109\/MSP.2014.2298891","volume":"31","author":"G Zhou","year":"2014","unstructured":"Zhou G, Cichocki A, Zhao Q, Xie S (2014) Nonnegative matrix and tensor factorizations: an algorithmic perspective. IEEE Signal Process Mag 31(3):54\u201365","journal-title":"IEEE Signal Process Mag"},{"issue":"3","key":"19121_CR39","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1137\/07070111X","volume":"51","author":"TG Kolda","year":"2009","unstructured":"Kolda TG, Bader BW (2009) Tensor decompositions and applications. SIAM 51(3):455\u2013500","journal-title":"SIAM"},{"key":"19121_CR40","doi-asserted-by":"publisher","first-page":"1702","DOI":"10.1109\/TASLP.2018.2842159","volume":"26","author":"D Wang","year":"2018","unstructured":"Wang D, Chen J (2018) Supervised speech separation based on deep learning: an overview. IEEE\/ACM Transactions on Audio, Speech, and Language Processing 26:1702\u20131726. https:\/\/doi.org\/10.1109\/TASLP.2018.2842159","journal-title":"IEEE\/ACM transactions on audio, speech, and language processing"},{"key":"19121_CR41","doi-asserted-by":"crossref","unstructured":"Nie S, Zhang H, Zhang X, Liu W (2014) Deep stacking networks with time series for speech separation, in Proceedings of ICASSP, pp. 6717-6721","DOI":"10.1109\/ICASSP.2014.6854890"},{"issue":"9","key":"19121_CR42","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1109\/TASLP.2016.2580946","volume":"24","author":"A Nugraha","year":"2016","unstructured":"Nugraha A, Liutkus A, Vincent E (2016) Multichannel audio source separation with deep neural networks. IEEE\/ACM Trans Audio Speech Lang Process 24(9):1652\u20131664","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"1","key":"19121_CR43","first-page":"92","volume":"23","author":"A Narayanan","year":"2015","unstructured":"Narayanan A, Wang D (2015) Improving robustness of deep neural network acoustic models via speech separation and joint adaptive training. IEEE\/ACM Trans Audio, Speech, Lang Process 23(1):92\u2013101","journal-title":"IEEE\/ACM Trans Audio, Speech, Lang Process"},{"key":"19121_CR44","unstructured":"Zhao RHY, Nakamura S (2003) Whitening processing for blind signal separation of speech signals. In: Proc. international conference on independent component analysis (ICA03), Nara, pp 331\u2013336"},{"issue":"3","key":"19121_CR45","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1109\/TASL.2010.2051355","volume":"19","author":"H Sawada","year":"2010","unstructured":"Sawada H, Araki S, Makino S (2010) Underdetermined convolutive blind source separation via frequency bin-wise clustering and permutation alignment. IEEE Trans Audio Speech Lang Process 19(3):516\u2013527","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"5","key":"19121_CR46","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1109\/TSA.2004.832994","volume":"12","author":"H Sawada","year":"2004","unstructured":"Sawada H, Mukai R, Araki S, Makino S (2004) A robust and precise method for solving the permutation problem of frequency-domain blind source separation. IEEE Trans Speech Audio Process 12(5):530\u2013538","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"1","key":"19121_CR47","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1109\/TASLP.2016.2620600","volume":"25","author":"A Al-Tmeme","year":"2017","unstructured":"Al-Tmeme A, Woo WL, Dlay SS, Gao B (2017) Underdetermined convolutive source separation using GEM-MU with variational approximated optimum model order NMF2D. IEEE\/ACM Trans Audio Speech Lang Process 25(1):35\u201349","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"19121_CR48","doi-asserted-by":"publisher","unstructured":"Mazur R, Mertins A (1996-1999) A sparsity based criterion for solving the permutation ambiguity in convolutive blind source separation. In: 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP), vol 2011, Prague. https:\/\/doi.org\/10.1109\/ICASSP.2011.5946902","DOI":"10.1109\/ICASSP.2011.5946902"},{"key":"19121_CR49","doi-asserted-by":"publisher","unstructured":"Kim M, Choi S (2006) ICA-based clustering for resolving permutation ambiguity in frequency-domain convolutive source separation. In: 18th international conference on pattern recognition (ICPR'06), Hong Kong, pp 950\u2013954. https:\/\/doi.org\/10.1109\/ICPR.2006.657","DOI":"10.1109\/ICPR.2006.657"},{"issue":"5","key":"19121_CR50","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.dsp.2014.04.009","volume":"31","author":"L Wang","year":"2014","unstructured":"Wang L (2014) Multi-band multi-centroid clustering based permutation alignment for frequency-domain blind speech separation. Digit Signal Process 31(5):79\u201392","journal-title":"Digit Signal Process"},{"issue":"7","key":"19121_CR51","doi-asserted-by":"publisher","first-page":"1830","DOI":"10.1109\/TSP.2004.828896","volume":"52","author":"O Yilmaz","year":"2004","unstructured":"Yilmaz O, Rickard S (2004) Blind Separation of Speech Mixtures via Time-Frequency Masking. Proc IEEE Trans Signal Processing 52(7):1830\u20131847","journal-title":"Proc IEEE Trans Signal Processing"},{"key":"19121_CR52","doi-asserted-by":"publisher","unstructured":"Abrard F, Deville Y (2003) Blind separation of dependent sources using the \"time-frequency ratio of mixtures\" approach. In: Seventh international symposium on signal processing and its applications, 2003 proceedings, vol 2, Paris, pp 81\u201384. https:\/\/doi.org\/10.1109\/ISSPA.2003.1224820","DOI":"10.1109\/ISSPA.2003.1224820"},{"key":"19121_CR53","doi-asserted-by":"publisher","unstructured":"Md Shohidul Islam, Yuanyuan Zhu, Md Imran Hossain, Rizwan Ullah, Zhongfu Ye (2020) Supervised single channel dual domains speech enhancement using sparse non-negative matrix factorization, Digital Signal Processing, vol. 100. https:\/\/doi.org\/10.1016\/j.dsp.2020.102697","DOI":"10.1016\/j.dsp.2020.102697"},{"issue":"3","key":"19121_CR54","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1109\/TASL.2009.2031510","volume":"18","author":"A Ozerov","year":"2010","unstructured":"Ozerov A, Fevotte C (2010) Multichannel nonnegative matrix factorization in convolutive mixtures for audio source separation. IEEE Trans Audio Speech Lang Process 18(3):550\u2013563","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"19121_CR55","doi-asserted-by":"publisher","unstructured":"Grais EM, Sen MU, Erdogan H (2014) Deep neural networks for single channel source separation. In: 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, Florence, pp 3734\u20133738. https:\/\/doi.org\/10.1109\/ICASSP.2014.6854299","DOI":"10.1109\/ICASSP.2014.6854299"},{"issue":"5","key":"19121_CR56","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1109\/TASLP.2015.2409778","volume":"23","author":"J Cho","year":"2015","unstructured":"Cho J, Chang DY (2015) Underdetermined convolutive BSS: Bayes risk minimization based on a mixture of super-Gaussian posterior approximation. IEEE\/ACM Trans Audio Speech Lang Process 23(5):828\u2013839","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"19121_CR57","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.mri.2018.08.023","volume":"54","author":"MM Cheriyan","year":"2018","unstructured":"Cheriyan MM, Michael PA, Kumar A (2018) Blind source separation with mixture models \u2013 A hybrid approach to MR brain classification. Magnetic Resonance Imaging 54:137\u2013147","journal-title":"Magnetic Resonance Imaging"},{"key":"19121_CR58","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.neunet.2011.12.005","volume":"28","author":"GV Pendse","year":"2012","unstructured":"Pendse GV (2012) PMOG: The projected mixture of Gaussians model with application to blind source separation. Neural Netw 28:40\u201360","journal-title":"Neural Netw"},{"key":"19121_CR59","doi-asserted-by":"publisher","unstructured":"Radfar MH, Wong W, Dansereau RM, Chan WY (2010) Scaled factorial hidden Markov models: a new technique for compensating gain differences in model-based single channel speech separation. In: 2010 IEEE international conference on acoustics, speech and signal processing, Dallas, pp 1918\u20131921. https:\/\/doi.org\/10.1109\/ICASSP.2010.5495323","DOI":"10.1109\/ICASSP.2010.5495323"},{"issue":"5","key":"19121_CR60","doi-asserted-by":"publisher","first-page":"1549","DOI":"10.1016\/j.dsp.2013.03.012","volume":"23","author":"F Gu","year":"2013","unstructured":"Gu F, Zhang H, Zhu D (2013) Blind separation of non-stationary sources using continuous density hidden Markov models. Digital Signal Processing 23(5):1549\u20131564","journal-title":"Digital Signal Processing"},{"key":"19121_CR61","doi-asserted-by":"publisher","unstructured":"Radfar MH, Dansereau RM (2007) Long-term gain estimation in model-based single channel speech separation. In: 2007 IEEE workshop on applications of signal processing to audio and acoustics, New Paltz, pp 143\u2013146. https:\/\/doi.org\/10.1109\/ASPAA.2007.4393019","DOI":"10.1109\/ASPAA.2007.4393019"},{"issue":"1","key":"19121_CR62","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s11265-008-0274-7","volume":"61","author":"MH Radfar","year":"2008","unstructured":"Radfar MH, Dansereau RM, Chan WY (2008) Monaural speech separation based on gain adapted minimum mean square error estimation. J Signal Process Syst Springer 61(1):21\u201337","journal-title":"J Signal Process Syst Springer"},{"key":"19121_CR63","doi-asserted-by":"publisher","unstructured":"Tzinis E, Venkataramani S, Smaragdis P (2019) Unsupervised deep clustering for source separation: direct learning from mixtures using spatial information. In: ICASSP 2019-2019 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, Brighton, pp 81-85. https:\/\/doi.org\/10.1109\/ICASSP.2019.8683201","DOI":"10.1109\/ICASSP.2019.8683201"},{"key":"19121_CR64","doi-asserted-by":"publisher","first-page":"86","DOI":"10.21437\/Interspeech.2020-2082","volume-title":"Proceedings of the annual conference of the international speech communication association","author":"Y Nakagome","year":"2020","unstructured":"Nakagome Y, Togami M, Ogawa T, Kobayashi T (2020) Mentoring-reverse mentoring for unsupervised multi-channel speech source separation. In: Proceedings of the annual conference of the international speech communication association. INTERSPEECH, pp 86\u201390. https:\/\/doi.org\/10.21437\/Interspeech.2020-2082"},{"issue":"1","key":"19121_CR65","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/TSP.2009.2030854","volume":"58","author":"S Arberet","year":"2010","unstructured":"Arberet S, Gribonval R, Bimbot F (2010) A robust method to count and locate audio sources in a multichannel underdetermined mixture. IEEE Trans on Signal Processing 58(1):121\u2013133","journal-title":"IEEE Trans on Signal Processing"},{"issue":"6","key":"19121_CR66","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.1109\/TASLP.2016.2533859","volume":"24","author":"L Wang","year":"2016","unstructured":"Wang L, Hon T-K, Reiss JD, Cavallaro A (2016) An iterative approach to source counting and localization using two distant microphones. IEEE\/ACM Trans Audio, Speech, Lang Process 24(6):1079\u20131093","journal-title":"IEEE\/ACM Trans Audio, Speech, Lang Process"},{"issue":"24","key":"19121_CR67","doi-asserted-by":"publisher","first-page":"6458","DOI":"10.1109\/TSP.2018.2876349","volume":"66","author":"B Laufer-Goldshtein","year":"2018","unstructured":"Laufer-Goldshtein B, Talmon R, Gannot S (2018) Source counting and separation based on simplex analysis. IEEE Trans Signal Process 66(24):6458\u20136473","journal-title":"IEEE Trans Signal Process"},{"issue":"1","key":"19121_CR68","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1109\/LSP.2018.2879547","volume":"26","author":"Y Chen","year":"2019","unstructured":"Chen Y, Wang W, Wang Z, Xia B (2019) A source counting method using acoustic vector sensor based on sparse modeling of DOA histogram. IEEE Signal Process Lett 26(1):69\u201373","journal-title":"IEEE Signal Process Lett"},{"issue":"2","key":"19121_CR69","first-page":"281","volume":"84","author":"D-J Kim","year":"2001","unstructured":"Kim D-J, Park Y-W, Park D-J (2001) A novel validity index for determination of the optimal number of clusters. IEICE Trans Inf Syst 84(2):281\u2013285","journal-title":"IEICE Trans Inf Syst"},{"issue":"10","key":"19121_CR70","doi-asserted-by":"publisher","first-page":"2027","DOI":"10.1016\/j.patcog.2004.03.012","volume":"37","author":"H Sun","year":"2004","unstructured":"Sun H, Wang S, Jiang Q (2004) FCM-based model selection algorithms for determining the number of clusters. Pattern Recogn 37(10):2027\u20132037","journal-title":"Pattern Recogn"},{"key":"19121_CR71","doi-asserted-by":"publisher","unstructured":"Mardia K, Kanti V, Jupp P (1999) Directional statistics. Wiley. https:\/\/doi.org\/10.1002\/9780470316979","DOI":"10.1002\/9780470316979"},{"key":"19121_CR72","doi-asserted-by":"crossref","unstructured":"Jammalamadaka S, Sengupta A (2001) Topics in Circular Statistics. World Scientific","DOI":"10.1142\/9789812779267"},{"key":"19121_CR73","doi-asserted-by":"publisher","unstructured":"Sgouros T, Mitianoudis N (2016) Underdetermined source separation using a sparse STFT framework and weighted laplacian directional modelling. In: 2016 24th European Signal Processing Conference (EUSIPCO), Budapest, Hungary, pp 1753-1757. https:\/\/doi.org\/10.1109\/EUSIPCO.2016.7760549.","DOI":"10.1109\/EUSIPCO.2016.7760549"},{"issue":"9","key":"19121_CR74","doi-asserted-by":"publisher","first-page":"2397","DOI":"10.1109\/TASL.2012.2203804","volume":"20","author":"N Mitianoudis","year":"2012","unstructured":"Mitianoudis N (2012) A Generalised Directional Laplacian Distribution: Estimation, Mixture Models and Audio Source Separation. IEEE Trans Audio Speech Lang Process 20(9):2397\u20132408","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"19121_CR75","unstructured":"Moattar MH, Homayounpour MM (2009) A simple but efficient real-time Voice Activity Detection algorithm. In: 2009 17th European signal processing conference, Glasgow, pp 2549\u20132553"},{"key":"19121_CR76","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/s00521-014-1707-9","volume":"26","author":"ZM Yang","year":"2015","unstructured":"Yang ZM, Guo YR, Li CN, Shao YH (2015) Local k-proximal plane clustering. Neural Comput & Applic 26:199\u2013211","journal-title":"Neural Comput & Applic"},{"key":"19121_CR77","doi-asserted-by":"publisher","first-page":"29845","DOI":"10.1109\/ACCESS.2019.2902620","volume":"7","author":"X Yang","year":"2019","unstructured":"Yang X, Yang H, Zhang F, Zhang L, Fan X, Ye Q, Fu L (2019) Piecewise linear regression based on plane clustering. IEEE Access 7:29845\u201329855. https:\/\/doi.org\/10.1109\/ACCESS.2019.2902620","journal-title":"IEEE Access"},{"key":"19121_CR78","volume-title":"Cluster analysis for applications","author":"MR Anderberg","year":"1973","unstructured":"Anderberg MR (1973) Cluster analysis for applications. Academic Press, New York"},{"key":"19121_CR79","unstructured":"Bradley, PS, Mangasarian, OL (1997) Street, WN, Clustering via concave minimization. In: M.C. Mozer, M.I. Jordan, and T. Petsche. Advances in Neural Information Processing Systems, Cambridge, MA. MIT Press, pp. 368\u2013374"},{"key":"19121_CR80","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1016\/0305-0548(91)90003-A","volume":"18","author":"TM Cavalier","year":"1991","unstructured":"Cavalier TM, Melloy BJ (1991) An iterative linear programming solution to the Euclidean regression model. Comput Oper Res 18:655\u2013661. https:\/\/doi.org\/10.1016\/0305-0548(91)90003-A","journal-title":"Comput Oper Res"},{"key":"19121_CR81","doi-asserted-by":"publisher","unstructured":"Sugar CA, James GM (2003) Finding the Number of Clusters in a Dataset: An Information-Theoretic Approach, J Am Stat Assoc, pp. 750\u2013763. https:\/\/doi.org\/10.1198\/016214503000000666","DOI":"10.1198\/016214503000000666"},{"key":"19121_CR82","unstructured":"Deza, E, Deza M (2006) Dictionary of Distances, 3rd ed. Elsevier"},{"key":"19121_CR83","doi-asserted-by":"publisher","first-page":"2881","DOI":"10.1007\/s00034-015-0173-7","volume":"35","author":"XS He","year":"2016","unstructured":"He XS, He F, Cai WH (2016) Underdetermined BSS Based on K-means and AP Clustering. Circuits Syst Signal Process 35:2881\u20132913","journal-title":"Circuits Syst Signal Process"},{"key":"19121_CR84","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1109\/ICASSP.2013.6637611","volume-title":"Sound source separation based on non-negative tensor factorization incorporating spatial cue as prior knowledge","author":"Y Mitsufuji","year":"2013","unstructured":"Mitsufuji Y, Roebel A (2013) Sound source separation based on non-negative tensor factorization incorporating spatial cue as prior knowledge. In: 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, Vancouver, pp 71\u201375. https:\/\/doi.org\/10.1109\/ICASSP.2013.6637611"},{"key":"19121_CR85","doi-asserted-by":"crossref","unstructured":"Mirzaei S, Van Hamme H, Norouzi Y (2013) Bayesian non-parametric matrix factorization for discovering words in spoken utterances,\u00a0IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, pp. 1\u20134","DOI":"10.1109\/WASPAA.2013.6701860"},{"key":"19121_CR86","doi-asserted-by":"publisher","first-page":"5393","DOI":"10.1007\/s00034-019-01106-0","volume":"38","author":"Y Xie","year":"2019","unstructured":"Xie Y, Xie K, Xie S (2019) Source Number Estimation and Effective Channel Order Determination Based on Higher-Order Tensors. Circuits Syst Signal Process 38:5393\u20135408","journal-title":"Circuits Syst Signal Process"},{"key":"19121_CR87","doi-asserted-by":"crossref","unstructured":"Matsuoka K (2002) Minimal distortion principle for blind source separation,\u00a0Proceedings of the 41st SICE Annual SICE Conference, Osaka, vol. 4, pp. 2138\u20132143","DOI":"10.1109\/SICE.2002.1195729"},{"key":"19121_CR88","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/s00034-017-0554-1","volume":"37","author":"XS He","year":"2018","unstructured":"He XS, He F, He AL (2018) Super-Gaussian BSS Using Fast-ICA with Chebyshev-Pade Approximant. Circuits Syst Signal Process 37:305\u2013341","journal-title":"Circuits Syst Signal Process"},{"key":"19121_CR89","doi-asserted-by":"publisher","unstructured":"Vincent, E, Sawada, H, Bofill P, Makino S, Rosca JP (2007) First stereo audio source separation evaluation campaign: Data, algorithms and results. In Proceedings of the International Conference on Independent Component Analysis and Signal Separation (ICA 2007), London, UK, pp. 552\u2013559, 9\u201312 September 2007. https:\/\/doi.org\/10.1007\/978-3-540-74494-8_69","DOI":"10.1007\/978-3-540-74494-8_69"},{"key":"19121_CR90","doi-asserted-by":"publisher","first-page":"2697","DOI":"10.1007\/s00034-016-0424-2","volume":"36","author":"F Gu","year":"2017","unstructured":"Gu F, Zhang H, Wang W, Wang S (2017) An Expectation-Maximization Algorithm for Blind Separation of Noisy Mixtures Using Gaussian Mixture Model. Circuits Syst Signal Process 36:2697\u20132726","journal-title":"Circuits Syst Signal Process"},{"issue":"1","key":"19121_CR91","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.csl.2003.12.001","volume":"19","author":"M Viswanathan","year":"2005","unstructured":"Viswanathan M, Viswanathan M (2005) Measuring speech quality for text-to-speech systems: development and assessment of a modified mean opinion score (MOS) scale. Comput Speech Lang 19(1):55\u201383","journal-title":"Comput Speech Lang"},{"issue":"2","key":"19121_CR92","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1016\/j.sigpro.2005.05.020","volume":"86","author":"D Smith","year":"2006","unstructured":"Smith D, Lukasiak J, Burnett IS (2006) An analysis of the limitations of blind signal separation application with speech. Signal Process 86(2):353\u2013359","journal-title":"Signal Process"},{"key":"19121_CR93","doi-asserted-by":"publisher","first-page":"5049","DOI":"10.1007\/s00034-022-02020-8","volume":"41","author":"JG Ri","year":"2022","unstructured":"Ri JG, Jang SH, Kim WC, Kim KS (2022) An Algorithm for Mixing Matrix Estimation in Underdetermined Blind Source Separation. Circuits Systems Signal Process 41:5049\u20135064","journal-title":"Circuits Systems Signal Process"},{"key":"19121_CR94","doi-asserted-by":"publisher","first-page":"7615","DOI":"10.1007\/s00034-023-02470-8","volume":"42","author":"J Lu","year":"2023","unstructured":"Lu J, Qian W, Yin Q, Xu K, Li S (2023) An Improved Underdetermined Blind Source Separation Method for Insufficiently Sparse Sources. Circuits Systems Signal Process 42:7615\u20137639","journal-title":"Circuits Systems Signal Process"},{"key":"19121_CR95","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1007\/s11042-022-13009-5","volume":"82","author":"M Niu","year":"2023","unstructured":"Niu M, Zhang Y (2023) Underdetermined blind speech source separation based on deep nearest neighbor clustering algorithm. Multimed Tools Appl 82:1171\u20131183","journal-title":"Multimed Tools Appl"},{"key":"19121_CR96","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/s11760-022-02207-1","volume":"17","author":"Q Wang","year":"2023","unstructured":"Wang Q, Zhang Y, Wang Y, Wu G (2023) A novel mixing matrix estimation method for underdetermined blind source separation based on sparse subspace clustering. SIViP 17:91\u201398","journal-title":"SIViP"},{"key":"19121_CR97","doi-asserted-by":"publisher","first-page":"6001","DOI":"10.1007\/s00034-023-02383-6","volume":"42","author":"L Li","year":"2023","unstructured":"Li L, Jia M, Liu J, Pai TW (2023) Separation of Multiple Speech Sources in Reverberant Environments Based on Sparse Component Enhancement. Circuits Systems Signal Process 42:6001\u20136028","journal-title":"Circuits Systems Signal Process"},{"key":"19121_CR98","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1109\/OJSP.2023.3343320","volume":"5","author":"NL Westhausen","year":"2024","unstructured":"Westhausen NL, Meyer BT (2024) Binaural Multichannel Blind Speaker Separation With a Causal Low-Latency and Low-Complexity Approach. IEEE Open J Signal Process 5:238\u2013247","journal-title":"IEEE Open J Signal Process"},{"key":"19121_CR99","doi-asserted-by":"publisher","first-page":"31035","DOI":"10.1007\/s11042-023-14649-x","volume":"82","author":"J Agrawal","year":"2023","unstructured":"Agrawal J, Gupta M, Garg H (2023) A review on speech separation in cocktail party environment: challenges and approaches. Multimed Tools Appl 82:31035\u201331067","journal-title":"Multimed Tools Appl"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19121-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-19121-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19121-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T02:55:07Z","timestamp":1743562507000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-19121-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,24]]},"references-count":99,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["19121"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-19121-y","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2024,4,24]]},"assertion":[{"value":"30 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}